Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating connections or relationships between various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    connected with "and" or "&"

    np_acts-logits-general · gemini-2.0-flash

    connecting alternatives or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BASEPATH
    -0.59
     Kombat
    -0.59
    rzost
    -0.55
     OnInit
    -0.54
     verticale
    -0.54
    celotti
    -0.53
     snipers
    -0.52
    ffindor
    -0.51
     Testamento
    -0.51
     Aeronautics
    -0.51
    POSITIVE LOGITS
     Related
    0.70
     related
    0.67
    /*
    0.61
     ancillary
    0.60
    related
    0.59
    enumii
    0.58
     allied
    0.57
    Chham
    0.57
     дописавши
    0.57
    Related
    0.55
    Act Density 0.438%

    No Known Activations